# Improving Single-Image Defocus Deblurring: How Dual-Pixel Images Help Through Multi-Task Learning

arXiv: https://arxiv.org/abs/2108.05251 · HTML: https://mlsanity.com/paper/2108.05251/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 38 references that are in the map.
- First posted on arXiv 11 Aug 2021.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [End-to-End Multi-Task Learning with Attention](https://mlsanity.com/paper/1803.10704/) (2018)
- [Scale-recurrent Network for Deep Image Deblurring](https://mlsanity.com/paper/1802.01770/) (2018)
- [Defocus Deblurring Using Dual-Pixel Data](https://mlsanity.com/paper/2005.00305/) (2020)
- [Spatio-Temporal Filter Adaptive Network for Video Deblurring](https://mlsanity.com/paper/1904.12257/) (2019)
- [Single Image Reflection Separation with Perceptual Losses](https://mlsanity.com/paper/1806.05376/) (2018)
- [Cascaded Deep Video Deblurring Using Temporal Sharpness Prior](https://mlsanity.com/paper/2004.02501/) (2020)
- [Synthetic Depth-of-Field with a Single-Camera Mobile Phone](https://mlsanity.com/paper/1806.04171/) (2018)
- [Learning Single Camera Depth Estimation using Dual-Pixels](https://mlsanity.com/paper/1904.05822/) (2019)
- [Dual Pixel Exploration: Simultaneous Depth Estimation and Image Restoration](https://mlsanity.com/paper/2012.00301/) (2020)
- [A Unified Approach of Multi-scale Deep and Hand-crafted Features for Defocus Estimation](https://mlsanity.com/paper/1704.08992/) (2017)
- [Du2Net: Learning Depth Estimation from Dual-Cameras and Dual-Pixels](https://mlsanity.com/paper/2003.14299/) (2020)
- [Attention! Stay Focus!](https://mlsanity.com/paper/2104.07925/) (2021)

## Built on by (most cited first, 20 of 20)

- [Deblurring 3D Gaussian Splatting](https://mlsanity.com/paper/2401.00834/) (2024)
- [Learning to Deblur using Light Field Generated and Real Defocus Images](https://mlsanity.com/paper/2204.00367/) (2022)
- [BAGS: Blur Agnostic Gaussian Splatting through Multi-Scale Kernel Modeling](https://mlsanity.com/paper/2403.04926/) (2024)
- [Multi-scale frequency separation network for image deblurring](https://mlsanity.com/paper/2206.00798/) (2022)
- [DC2: Dual-Camera Defocus Control by Learning to Refocus](https://mlsanity.com/paper/2304.03285/) (2023)
- [Sharp-NeRF: Grid-based Fast Deblurring Neural Radiance Fields Using Sharpness Prior](https://mlsanity.com/paper/2401.00825/) (2024)
- [LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network](https://mlsanity.com/paper/2307.09815/) (2023)
- [BSRAW: Improving Blind RAW Image Super-Resolution](https://mlsanity.com/paper/2312.15487/) (2023)
- [Revisiting Image Deblurring with an Efficient ConvNet](https://mlsanity.com/paper/2302.02234/) (2023)
- [Unsupervised Imaging Inverse Problems with Diffusion Distribution Matching](https://mlsanity.com/paper/2506.14605/) (2025)
- [Point-and-Shoot All-in-Focus Photo Synthesis from Smartphone Camera Pair](https://mlsanity.com/paper/2304.04917/) (2023)
- [Multi-View Motion Synthesis via Applying Rotated Dual-Pixel Blur Kernels](https://mlsanity.com/paper/2111.07837/) (2021)
- [Continuous Cost Aggregation for Dual-Pixel Disparity Extraction](https://mlsanity.com/paper/2306.07921/) (2023)
- [Towards Unified Image Deblurring using a Mixture-of-Experts Decoder](https://mlsanity.com/paper/2508.06228/) (2025)
- [Learnable Blur Kernel for Single-Image Defocus Deblurring in the Wild](https://mlsanity.com/paper/2211.14017/) (2022)
- [Simulating Dual-Pixel Images From Ray Tracing For Depth Estimation](https://mlsanity.com/paper/2503.11213/) (2025)
- [Revisiting Disparity from Dual-Pixel Images: Physics-Informed Lightweight Depth Estimation](https://mlsanity.com/paper/2411.04714/) (2024)
- [Image Restoration via Multi-domain Learning](https://mlsanity.com/paper/2505.05504/) (2025)
- [DP-SfM: Dual-Pixel Structure-from-Motion without Scale Ambiguity](https://mlsanity.com/paper/2605.01852/) (2026)
- [FoundDP: Revisiting Weak Disparity Observability in Dual-Pixel Depth Estimation](https://mlsanity.com/paper/2607.01900/) (2026)

## Abstract (arXiv)

Many camera sensors use a dual-pixel (DP) design that operates as a rudimentary light field providing two sub-aperture views of a scene in a single capture. The DP sensor was developed to improve how cameras perform autofocus. Since the DP sensor's introduction, researchers have found additional uses for the DP data, such as depth estimation, reflection removal, and defocus deblurring. We are interested in the latter task of defocus deblurring. In particular, we propose a single-image deblurring network that incorporates the two sub-aperture views into a multi-task framework. Specifically, we show that jointly learning to predict the two DP views from a single blurry input image improves the network's ability to learn to deblur the image. Our experiments show this multi-task strategy achieves +1dB PSNR improvement over state-of-the-art defocus deblurring methods. In addition, our multi-task framework allows accurate DP-view synthesis (e.g., ~39dB PSNR) from the single input image. These high-quality DP views can be used for other DP-based applications, such as reflection removal. As part of this effort, we have captured a new dataset of 7,059 high-quality images to support our training for the DP-view synthesis task. Our dataset, code, and trained models are publicly available at https://github.com/Abdullah-Abuolaim/multi-task-defocus-deblurring-dual-pixel-nimat.